teradataml 20.0.0.2__py3-none-any.whl → 20.0.0.4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of teradataml might be problematic. Click here for more details.
- teradataml/LICENSE-3RD-PARTY.pdf +0 -0
- teradataml/README.md +315 -2
- teradataml/__init__.py +4 -0
- teradataml/_version.py +1 -1
- teradataml/analytics/analytic_function_executor.py +95 -8
- teradataml/analytics/byom/__init__.py +1 -1
- teradataml/analytics/json_parser/metadata.py +12 -3
- teradataml/analytics/json_parser/utils.py +7 -2
- teradataml/analytics/sqle/__init__.py +5 -1
- teradataml/analytics/table_operator/__init__.py +1 -1
- teradataml/analytics/uaf/__init__.py +1 -1
- teradataml/analytics/utils.py +4 -0
- teradataml/analytics/valib.py +18 -4
- teradataml/automl/__init__.py +51 -6
- teradataml/automl/data_preparation.py +59 -35
- teradataml/automl/data_transformation.py +58 -33
- teradataml/automl/feature_engineering.py +27 -12
- teradataml/automl/model_training.py +73 -46
- teradataml/common/constants.py +88 -29
- teradataml/common/garbagecollector.py +2 -1
- teradataml/common/messagecodes.py +19 -3
- teradataml/common/messages.py +6 -1
- teradataml/common/sqlbundle.py +64 -12
- teradataml/common/utils.py +246 -47
- teradataml/common/warnings.py +11 -0
- teradataml/context/context.py +161 -27
- teradataml/data/amazon_reviews_25.csv +26 -0
- teradataml/data/byom_example.json +11 -0
- teradataml/data/dataframe_example.json +18 -2
- teradataml/data/docs/byom/docs/DataRobotPredict.py +2 -2
- teradataml/data/docs/byom/docs/DataikuPredict.py +40 -1
- teradataml/data/docs/byom/docs/H2OPredict.py +2 -2
- teradataml/data/docs/byom/docs/ONNXEmbeddings.py +242 -0
- teradataml/data/docs/byom/docs/ONNXPredict.py +2 -2
- teradataml/data/docs/byom/docs/PMMLPredict.py +2 -2
- teradataml/data/docs/sqle/docs_17_20/NaiveBayes.py +1 -1
- teradataml/data/docs/sqle/docs_17_20/Shap.py +34 -6
- teradataml/data/docs/sqle/docs_17_20/TDNaiveBayesPredict.py +4 -4
- teradataml/data/docs/sqle/docs_17_20/TextParser.py +3 -3
- teradataml/data/docs/tableoperator/docs_17_20/Image2Matrix.py +118 -0
- teradataml/data/docs/uaf/docs_17_20/CopyArt.py +145 -0
- teradataml/data/docs/uaf/docs_17_20/DWT2D.py +4 -1
- teradataml/data/docs/uaf/docs_17_20/DickeyFuller.py +18 -21
- teradataml/data/hnsw_alter_data.csv +5 -0
- teradataml/data/hnsw_data.csv +10 -0
- teradataml/data/jsons/byom/h2opredict.json +1 -1
- teradataml/data/jsons/byom/onnxembeddings.json +266 -0
- teradataml/data/jsons/sqle/17.20/TD_Shap.json +0 -1
- teradataml/data/jsons/sqle/17.20/TD_TextParser.json +1 -1
- teradataml/data/jsons/sqle/20.00/TD_HNSW.json +296 -0
- teradataml/data/jsons/sqle/20.00/TD_HNSWPredict.json +206 -0
- teradataml/data/jsons/sqle/20.00/TD_HNSWSummary.json +32 -0
- teradataml/data/jsons/sqle/20.00/TD_KMeans.json +250 -0
- teradataml/data/jsons/sqle/20.00/TD_SMOTE.json +266 -0
- teradataml/data/jsons/sqle/20.00/TD_VectorDistance.json +278 -0
- teradataml/data/jsons/storedprocedure/17.20/TD_COPYART.json +71 -0
- teradataml/data/jsons/tableoperator/17.20/IMAGE2MATRIX.json +53 -0
- teradataml/data/jsons/uaf/17.20/TD_DICKEY_FULLER.json +10 -19
- teradataml/data/jsons/uaf/17.20/TD_SAX.json +3 -1
- teradataml/data/jsons/uaf/17.20/TD_WINDOWDFFT.json +15 -5
- teradataml/data/medical_readings.csv +101 -0
- teradataml/data/patient_profile.csv +101 -0
- teradataml/data/scripts/lightgbm/dataset.template +157 -0
- teradataml/data/scripts/lightgbm/lightgbm_class_functions.template +247 -0
- teradataml/data/scripts/lightgbm/lightgbm_function.template +216 -0
- teradataml/data/scripts/lightgbm/lightgbm_sklearn.template +159 -0
- teradataml/data/scripts/sklearn/sklearn_fit.py +194 -167
- teradataml/data/scripts/sklearn/sklearn_fit_predict.py +136 -115
- teradataml/data/scripts/sklearn/sklearn_function.template +14 -19
- teradataml/data/scripts/sklearn/sklearn_model_selection_split.py +155 -137
- teradataml/data/scripts/sklearn/sklearn_transform.py +129 -42
- teradataml/data/target_udt_data.csv +8 -0
- teradataml/data/templates/open_source_ml.json +3 -2
- teradataml/data/teradataml_example.json +8 -0
- teradataml/data/vectordistance_example.json +4 -0
- teradataml/dataframe/copy_to.py +8 -3
- teradataml/dataframe/data_transfer.py +11 -1
- teradataml/dataframe/dataframe.py +1049 -285
- teradataml/dataframe/dataframe_utils.py +152 -20
- teradataml/dataframe/functions.py +578 -35
- teradataml/dataframe/setop.py +11 -6
- teradataml/dataframe/sql.py +185 -16
- teradataml/dbutils/dbutils.py +1049 -115
- teradataml/dbutils/filemgr.py +48 -1
- teradataml/hyperparameter_tuner/optimizer.py +12 -1
- teradataml/lib/aed_0_1.dll +0 -0
- teradataml/opensource/__init__.py +1 -1
- teradataml/opensource/_base.py +1466 -0
- teradataml/opensource/_class.py +464 -0
- teradataml/opensource/{sklearn/constants.py → _constants.py} +21 -14
- teradataml/opensource/_lightgbm.py +949 -0
- teradataml/opensource/_sklearn.py +1008 -0
- teradataml/opensource/{sklearn/_wrapper_utils.py → _wrapper_utils.py} +5 -6
- teradataml/options/__init__.py +54 -38
- teradataml/options/configure.py +131 -27
- teradataml/options/display.py +13 -2
- teradataml/plot/axis.py +47 -8
- teradataml/plot/figure.py +33 -0
- teradataml/plot/plot.py +63 -13
- teradataml/scriptmgmt/UserEnv.py +5 -5
- teradataml/scriptmgmt/lls_utils.py +130 -40
- teradataml/store/__init__.py +12 -0
- teradataml/store/feature_store/__init__.py +0 -0
- teradataml/store/feature_store/constants.py +291 -0
- teradataml/store/feature_store/feature_store.py +2318 -0
- teradataml/store/feature_store/models.py +1505 -0
- teradataml/table_operators/Apply.py +32 -18
- teradataml/table_operators/Script.py +3 -1
- teradataml/table_operators/TableOperator.py +3 -1
- teradataml/table_operators/query_generator.py +3 -0
- teradataml/table_operators/table_operator_query_generator.py +3 -1
- teradataml/table_operators/table_operator_util.py +37 -38
- teradataml/table_operators/templates/dataframe_register.template +69 -0
- teradataml/utils/dtypes.py +51 -2
- teradataml/utils/internal_buffer.py +18 -0
- teradataml/utils/validators.py +99 -8
- {teradataml-20.0.0.2.dist-info → teradataml-20.0.0.4.dist-info}/METADATA +321 -5
- {teradataml-20.0.0.2.dist-info → teradataml-20.0.0.4.dist-info}/RECORD +121 -94
- teradataml/libaed_0_1.dylib +0 -0
- teradataml/libaed_0_1.so +0 -0
- teradataml/opensource/sklearn/__init__.py +0 -1
- teradataml/opensource/sklearn/_class.py +0 -255
- teradataml/opensource/sklearn/_sklearn_wrapper.py +0 -1800
- {teradataml-20.0.0.2.dist-info → teradataml-20.0.0.4.dist-info}/WHEEL +0 -0
- {teradataml-20.0.0.2.dist-info → teradataml-20.0.0.4.dist-info}/top_level.txt +0 -0
- {teradataml-20.0.0.2.dist-info → teradataml-20.0.0.4.dist-info}/zip-safe +0 -0
|
@@ -1368,5 +1368,13 @@
|
|
|
1368
1368
|
"id": "INTEGER",
|
|
1369
1369
|
"urls": "VARCHAR(60)",
|
|
1370
1370
|
"part": "VARCHAR(20)"
|
|
1371
|
+
},
|
|
1372
|
+
"hnsw_data": {
|
|
1373
|
+
"id": "INTEGER",
|
|
1374
|
+
"array_col": "Vector"
|
|
1375
|
+
},
|
|
1376
|
+
"hnsw_alter_data": {
|
|
1377
|
+
"id": "INTEGER",
|
|
1378
|
+
"array_col": "Vector"
|
|
1371
1379
|
}
|
|
1372
1380
|
}
|
teradataml/dataframe/copy_to.py
CHANGED
|
@@ -487,6 +487,11 @@ def copy_to_sql(df, table_name,
|
|
|
487
487
|
table_type=TeradataConstants.TERADATA_TABLE,
|
|
488
488
|
quote=False)
|
|
489
489
|
|
|
490
|
+
# If configure.temp_object_type="VT", _generate_temp_table_name() retruns the
|
|
491
|
+
# table name in fully qualified format. Because of this , test cases started
|
|
492
|
+
# failing with Blank name in quotation mark. Hence, extracted only the table name.
|
|
493
|
+
table_name = UtilFuncs._extract_table_name(table_name)
|
|
494
|
+
|
|
490
495
|
# Let's create the SQLAlchemy table object to recreate the table
|
|
491
496
|
if not table_exists or if_exists.lower() == 'replace':
|
|
492
497
|
if not is_pti:
|
|
@@ -1459,9 +1464,9 @@ def _extract_column_info(df, types = None, index = False, index_label = None):
|
|
|
1459
1464
|
# If the datatype is not specified then check if the datatype is datetime64 and timezone is present then map it to
|
|
1460
1465
|
# TIMESTAMP(timezone=True) else map it according to default value.
|
|
1461
1466
|
col_types = [types.get(col_name) if types and col_name in types else
|
|
1462
|
-
TIMESTAMP(timezone=True) if pt.is_datetime64_ns_dtype(df.dtypes[key])
|
|
1467
|
+
TIMESTAMP(timezone=True) if pt.is_datetime64_ns_dtype(df.dtypes.iloc[key])
|
|
1463
1468
|
and (df[col_name].dt.tz is not None)
|
|
1464
|
-
else _get_sqlalchemy_mapping_types(str(df.dtypes[key]))
|
|
1469
|
+
else _get_sqlalchemy_mapping_types(str(df.dtypes.iloc[key]))
|
|
1465
1470
|
for key, col_name in enumerate(list(df.columns))]
|
|
1466
1471
|
|
|
1467
1472
|
ind_names = []
|
|
@@ -1469,7 +1474,7 @@ def _extract_column_info(df, types = None, index = False, index_label = None):
|
|
|
1469
1474
|
if index:
|
|
1470
1475
|
ind_names, ind_types = _get_index_labels(df, index_label)
|
|
1471
1476
|
ind_types = [types.get(ind_name) if types and ind_name in types
|
|
1472
|
-
else TIMESTAMP(timezone=True) if pt.is_datetime64_ns_dtype(df.dtypes[key])
|
|
1477
|
+
else TIMESTAMP(timezone=True) if pt.is_datetime64_ns_dtype(df.dtypes.iloc[key])
|
|
1473
1478
|
and (df[ind_name].dt.tz is not None)
|
|
1474
1479
|
else _get_sqlalchemy_mapping_types(str(ind_types[key]))
|
|
1475
1480
|
for key, ind_name in enumerate(ind_names)]
|
|
@@ -328,6 +328,7 @@ def fastexport(df, export_to="pandas", index_column=None,
|
|
|
328
328
|
# using fastexport datatransfer protocol.
|
|
329
329
|
# "require" is always True, because with this function user requires
|
|
330
330
|
# fastexport.
|
|
331
|
+
|
|
331
332
|
return dt_obj._fastexport_get_pandas_df(require=True, **kwargs)
|
|
332
333
|
|
|
333
334
|
# Convert teradataml DataFrame to CSV file.
|
|
@@ -2553,7 +2554,6 @@ class _DataTransferUtils():
|
|
|
2553
2554
|
_create_staging_table_and_load_csv_data(column_info={"id": INTEGER}, primary_index = ['id'])
|
|
2554
2555
|
|
|
2555
2556
|
"""
|
|
2556
|
-
stag_table_name = ""
|
|
2557
2557
|
stage_table_created = False
|
|
2558
2558
|
try:
|
|
2559
2559
|
# Generate the temporary table.
|
|
@@ -2562,6 +2562,11 @@ class _DataTransferUtils():
|
|
|
2562
2562
|
quote=False,
|
|
2563
2563
|
table_type=TeradataConstants.TERADATA_TABLE)
|
|
2564
2564
|
|
|
2565
|
+
# If configure.temp_object_type="VT", _generate_temp_table_name() retruns the
|
|
2566
|
+
# table name in fully qualified format. Because of this , test cases started
|
|
2567
|
+
# failing with Blank name in quotation mark. Hence, extracted only the table name.
|
|
2568
|
+
stag_table_name = UtilFuncs._extract_table_name(stag_table_name)
|
|
2569
|
+
|
|
2565
2570
|
# Information about uniqueness of primary index and
|
|
2566
2571
|
# SET/MULTISET property of existing table is not available,
|
|
2567
2572
|
# so over-assuming to be False.
|
|
@@ -2707,6 +2712,11 @@ class _DataTransferUtils():
|
|
|
2707
2712
|
quote=False,
|
|
2708
2713
|
table_type=TeradataConstants.TERADATA_TABLE)
|
|
2709
2714
|
|
|
2715
|
+
# If configure.temp_object_type="VT", _generate_temp_table_name() retruns the
|
|
2716
|
+
# table name in fully qualified format. Because of this , test cases started
|
|
2717
|
+
# failing with Blank name in quotation mark. Hence, extracted only the table name.
|
|
2718
|
+
stag_table_name = UtilFuncs._extract_table_name(stag_table_name)
|
|
2719
|
+
|
|
2710
2720
|
# Get the teradataml dataframe from staging table using read_csv()
|
|
2711
2721
|
read_csv_output = read_csv(filepath=self.df, table_name=stag_table_name,
|
|
2712
2722
|
types=self.types, sep=self.sep,
|